Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
jinaai
/
xlm-roberta-flash-implementation
like
25
Follow
Jina AI
431
Transformers
94 languages
xlm-roberta
Inference Endpoints
License:
cc-by-nc-4.0
🇪🇺 Region: EU
Model card
Files
Files and versions
Community
56
Train
Deploy
Use this model
dc4080e
xlm-roberta-flash-implementation
10 contributors
History:
45 commits
jupyterjazz
fix: override use_flash_attn in lora
dc4080e
verified
4 months ago
.gitattributes
Safe
1.52 kB
initial commit
9 months ago
README.md
Safe
557 Bytes
refine-codebase (#33)
4 months ago
block.py
Safe
17.8 kB
refine-codebase (#33)
4 months ago
configuration_xlm_roberta.py
Safe
6.41 kB
feat: configurable use_reentrant (#37)
4 months ago
convert_roberta_weights_to_flash.py
Safe
6.94 kB
Support for SequenceClassification (#7)
8 months ago
embedding.py
Safe
3.88 kB
refine-codebase (#33)
4 months ago
mha.py
Safe
34.4 kB
cpu-inference (#35)
4 months ago
mlp.py
Safe
7.62 kB
refine-codebase (#33)
4 months ago
modeling_lora.py
Safe
14.5 kB
fix: override use_flash_attn in lora
4 months ago
modeling_xlm_roberta.py
Safe
49.8 kB
cpu-inference (#35)
4 months ago
rotary.py
Safe
23.9 kB
Fix rotary backward
4 months ago
stochastic_depth.py
Safe
3.76 kB
refine-codebase (#33)
4 months ago
xlm_padding.py
Safe
10 kB
refine-codebase (#33)
4 months ago
